Comment Comment by adefa True :)After some performance improvements, it is realtime on my DGX Spark with an RTF of .416 -- now getting ~19.5 tokens per second. Check it out, see if it's better for you. parent adefa 8 months ago
After some performance improvements, it is realtime on my DGX Spark with an RTF of .416 -- now getting ~19.5 tokens per second. Check it out, see if it's better for you.